{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:Y4DEUJWAWTBUVLA5327TRFLMEN","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e48866d9a1718a2c13f71a2bf4bc1c8434fd27946911f195c469996268aaf6b3","cross_cats_sorted":["quant-ph"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2026-01-17T07:32:18Z","title_canon_sha256":"cc05d6ae44c146deef6d82166ac1ae397e2c197d2dec1a8ffcd73d3b1b22f0c8"},"schema_version":"1.0","source":{"id":"2601.11942","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.11942","created_at":"2026-05-18T03:09:24Z"},{"alias_kind":"arxiv_version","alias_value":"2601.11942v3","created_at":"2026-05-18T03:09:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.11942","created_at":"2026-05-18T03:09:24Z"},{"alias_kind":"pith_short_12","alias_value":"Y4DEUJWAWTBU","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"Y4DEUJWAWTBUVLA5","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"Y4DEUJWA","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:5bc449466c1fa4d78a005883fb14223e01ce16a1d1fbbfc82d1341f7295c1df8","target":"graph","created_at":"2026-05-18T03:09:24Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Across finite-size statevector audits on PDE-informed regression benchmarks and small-data tabular tasks, the Hybrid QNN lowers error relative to Pure QNN baselines under matched quantum-model budgets."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The classical embedding successfully acts as a learnable geometric preconditioner that reshapes the empirical Gram matrix to improve residual contraction in the linearized quantum-parameter dynamics, without the capacity control introducing new ill-conditioning that offsets the benefit."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"A hybrid variational quantum regression design with classical geometric preconditioning and curriculum optimization improves trainability over pure quantum models while remaining behind strong classical baselines."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A capacity-controlled classical embedding acts as a learnable geometric preconditioner to improve trainability of variational quantum circuits for regression."}],"snapshot_sha256":"dc8f25d92ea678c7743c19d0d63b5cfc23dcb1eb753f49038e7a322cba68869c"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"30210bb21e03697ad68e283e87307bace8f269cf7214f7e9c942b371ab7e922c"},"paper":{"abstract_excerpt":"Variational quantum circuits are increasingly studied as continuous-function approximators, but quantum regression remains difficult to train when global losses, finite-shot stochasticity, and circuit-depth growth combine to produce weak or ill-conditioned gradient signals. We study this trainability problem in a controlled hybrid quantum--classical regression design. The central ingredient is a capacity-controlled classical embedding that acts as a learnable geometric preconditioner: it reshapes the input distribution seen by a data-reuploading variational circuit while preserving a low-dimen","authors_text":"Qingyu Meng, Yangshuai Wang","cross_cats":["quant-ph"],"headline":"A capacity-controlled classical embedding acts as a learnable geometric preconditioner to improve trainability of variational quantum circuits for regression.","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2026-01-17T07:32:18Z","title":"Geometric Preconditioning and Curriculum Optimization for Trainable Variational Quantum Regression"},"references":{"count":36,"internal_anchors":0,"resolved_work":36,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"The power of quantum neural networks.Nature Computa- tional Science, 1(6):403–409,","work_id":"9ebc46e0-a671-4c96-bfa6-1c3f18b36d6d","year":2021},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"UCI machine learning repository,","work_id":"d26af7bf-88e1-4286-ba07-aa5d55c1c272","year":2007},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Training deep quan- tum neural networks.Nature communications, 11(1):808,","work_id":"b321b655-fb0b-40c1-8839-671237b4aa5a","year":2020},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Trainable embedding quantum physics informed neural networks for solving nonlinear pdes.Sci- entific Reports, 15(1):18823,","work_id":"6d0ae0d6-bd54-48bb-b715-bb1fd7d2dd12","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"J., Farkas, M., Killoran, N","work_id":"c361f579-4f45-4544-a6b5-27565fec14a4","year":2023}],"snapshot_sha256":"0e027e0a678bfa0e7541a350895a11e3ac6a1717afa9b922a5edbc783d77492e"},"source":{"id":"2601.11942","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-16T13:10:28.472850Z","id":"24e981f6-c95e-408d-af21-3369e6478de7","model_set":{"reader":"grok-4.3"},"one_line_summary":"A hybrid variational quantum regression design with classical geometric preconditioning and curriculum optimization improves trainability over pure quantum models while remaining behind strong classical baselines.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A capacity-controlled classical embedding acts as a learnable geometric preconditioner to improve trainability of variational quantum circuits for regression.","strongest_claim":"Across finite-size statevector audits on PDE-informed regression benchmarks and small-data tabular tasks, the Hybrid QNN lowers error relative to Pure QNN baselines under matched quantum-model budgets.","weakest_assumption":"The classical embedding successfully acts as a learnable geometric preconditioner that reshapes the empirical Gram matrix to improve residual contraction in the linearized quantum-parameter dynamics, without the capacity control introducing new ill-conditioning that offsets the benefit."}},"verdict_id":"24e981f6-c95e-408d-af21-3369e6478de7"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:1dbd77570dd6efa397a02d580076eb3ffaa166b8a6411542c829d3a9c5d9e82d","target":"record","created_at":"2026-05-18T03:09:24Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e48866d9a1718a2c13f71a2bf4bc1c8434fd27946911f195c469996268aaf6b3","cross_cats_sorted":["quant-ph"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2026-01-17T07:32:18Z","title_canon_sha256":"cc05d6ae44c146deef6d82166ac1ae397e2c197d2dec1a8ffcd73d3b1b22f0c8"},"schema_version":"1.0","source":{"id":"2601.11942","kind":"arxiv","version":3}},"canonical_sha256":"c7064a26c0b4c34aac1ddebf38956c2370f17c9e96a135f36805133a5584f500","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c7064a26c0b4c34aac1ddebf38956c2370f17c9e96a135f36805133a5584f500","first_computed_at":"2026-05-18T03:09:24.385650Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:09:24.385650Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gzeuEd3Yq3gCS+7pXcLzrYz6vz76uduZGQUyHMA0Sp5qiiUB5XGvyOaw98Yq8IOnPZlQDcDWDb6VuxpGl7ztAA==","signature_status":"signed_v1","signed_at":"2026-05-18T03:09:24.386329Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.11942","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1dbd77570dd6efa397a02d580076eb3ffaa166b8a6411542c829d3a9c5d9e82d","sha256:5bc449466c1fa4d78a005883fb14223e01ce16a1d1fbbfc82d1341f7295c1df8"],"state_sha256":"f47c2ec08183a2a8b232afc4bdd14e566caf2160d47f8e9c9af1e4ccb13b9999"}